English
Related papers

Related papers: Vision-Language Models are Zero-Shot Reward Models…

200 papers

Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a…

Computation and Language · Computer Science 2025-06-12 Ruipeng Jia , Yunyi Yang , Yongbo Gai , Kai Luo , Shihao Huang , Jianhe Lin , Xiaoxi Jiang , Guanjun Jiang

Multimodal Large Language Models (MLLMs) exhibit impressive performance across various visual tasks. Subsequent investigations into enhancing their visual reasoning abilities have significantly expanded their performance envelope. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Yang Chen , Yufan Shen , Wenxuan Huang , Sheng Zhou , Qunshu Lin , Xinyu Cai , Zhi Yu , Jiajun Bu , Botian Shi , Yu Qiao

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Robotics · Computer Science 2025-09-29 Asher J. Hancock , Xindi Wu , Lihan Zha , Olga Russakovsky , Anirudha Majumdar

Vision-Language Models (VLMs) excel in many direct multimodal tasks but struggle to translate this prowess into effective decision-making within interactive, visually rich environments like games. This ``knowing-doing'' gap significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Liang Chen , Hongcheng Gao , Tianyu Liu , Zhiqi Huang , Flood Sung , Xinyu Zhou , Yuxin Wu , Baobao Chang

Reward machines (RMs) are automata structures that encode (non-Markovian) reward functions for reinforcement learning (RL). RMs can reward any behaviour representable in regular languages and, when paired with RL algorithms that exploit RM…

Artificial Intelligence · Computer Science 2025-11-13 Giovanni Varricchione , Toryn Q. Klassen , Natasha Alechina , Mehdi Dastani , Brian Logan , Sheila A. McIlraith

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Robotics · Computer Science 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Machine Learning · Computer Science 2024-05-28 Tianbao Xie , Siheng Zhao , Chen Henry Wu , Yitao Liu , Qian Luo , Victor Zhong , Yanchao Yang , Tao Yu

Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deployment of LLMs, in-the-wild interactions have emerged as a…

Computation and Language · Computer Science 2026-02-10 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Lei Hou , Juanzi Li

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Artificial Intelligence · Computer Science 2025-04-18 Baining Zhao , Ziyou Wang , Jianjie Fang , Chen Gao , Fanhang Man , Jinqiang Cui , Xin Wang , Xinlei Chen , Yong Li , Wenwu Zhu

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…

Machine Learning · Computer Science 2021-11-12 Ozsel Kilinc , Giovanni Montana

Large language models (LLMs) have recently demonstrated remarkable capabilities in machine translation (MT). However, most advanced MT-specific LLMs heavily rely on external supervision signals during training, such as human-annotated…

Computation and Language · Computer Science 2026-04-28 Wenjie Yang , Mao Zheng , Mingyang Song , Zheng Li , Sitong Wang

Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Adeel Yousaf , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan , Mubarak Shah

Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Kai Han , Jianyuan Guo , Yehui Tang , Wei He , Enhua Wu , Yunhe Wang

Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experience. However, deploying RL agents in production…

Artificial Intelligence · Computer Science 2025-07-01 António Afonso , Iolanda Leite , Alessandro Sestini , Florian Fuchs , Konrad Tollmar , Linus Gisslén

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite

Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Stephanie Fu , Tyler Bonnen , Devin Guillory , Trevor Darrell

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation.…

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

In robot manipulation, Reinforcement Learning (RL) often suffers from low sample efficiency and uncertain convergence, especially in large observation and action spaces. Foundation Models (FMs) offer an alternative, demonstrating promise in…

Robotics · Computer Science 2025-04-18 Runyu Ma , Jelle Luijkx , Zlatan Ajanovic , Jens Kober

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Computation and Language · Computer Science 2024-03-27 Chengxu Zhuang , Evelina Fedorenko , Jacob Andreas